Over/Under Goals Calculator — Football Betting Probabilities

Using the Over/Under Goals Calculator is straightforward. You need two inputs: the expected goals (xG) for the home team and the away team. Expected goals is a statistical measure of how many goals a team is predicted to score based on the quality and quantity of their chances. You can find xG data on sites like FBref, Understat, Sofascore, or directly from your preferred football data provider.

Next, select the goals threshold — the most common market is Over/Under 2.5 goals, but you can also analyse 0.5, 1.5, 3.5, and 4.5 lines. As you type, the tool instantly shows:

• The probability of going Over your selected threshold
• The probability of going Under your selected threshold
• Fair odds — what the odds should be with zero bookmaker margin, in the format you pick with the Odds format switch
• The top 5 most likely scorelines with individual probabilities

Compare the fair odds produced by the calculator with the odds offered by bookmakers. If a bookmaker is offering 1.85 on Over 2.5 goals and the fair odds are 1.70, the market implies a higher probability than your model — that could be value on the Under. Always cross-reference with team news, weather conditions, and match context before placing any wager.

The Over/Under Goals Calculator uses the Poisson distribution, a probability model widely used in football analytics. The Poisson distribution describes the probability of a given number of events occurring in a fixed interval when the average rate is known.

1. Poisson PMF: The probability of exactly k goals for a team with expected goals λ is:
   P(X = k) = (λ^k × e^(−λ)) / k!
2. Independence assumption: Home and away goals are treated as independent events. The probability of a specific scoreline (h goals home, a goals away) is:
   P(h, a) = P(Home = h) × P(Away = a)
3. Over probability: Sum all scoreline probabilities where total goals exceed the threshold:
   P(Over T) = Σ P(h, a) for all h, a where h + a > T
4. Under probability: The complement — P(Under T) = 1 − P(Over T)
5. Fair odds: Fair Odds = 1 / probability (where probability is expressed as a decimal, e.g. 0.55 not 55%)

The calculator evaluates all scoreline combinations from 0–0 up to 8–8 (81 combinations), which captures over 99.9% of the probability mass for any realistic xG input. Higher goal scenarios (9+ goals) are negligible in practice.

Example 1 — Premier League Mid-Table Clash

Crystal Palace (home, xG 1.2) vs Brentford (away, xG 1.4). You want to assess the Over/Under 2.5 market.

• Total expected goals: 1.2 + 1.4 = 2.6
• Poisson model gives approximately 48% probability of Over 2.5
• Fair Over 2.5 odds: ~2.08; Fair Under 2.5 odds: ~1.93
• If a bookmaker is pricing Over 2.5 at 2.10, that is above the fair odds — the bookmaker implies a lower probability than your model, suggesting potential value on Over 2.5

Example 2 — Champions League Heavyweight Tie

Manchester City (home, xG 2.1) vs Real Madrid (away, xG 1.8). You are considering the Over 3.5 goals market.

• Total expected goals: 2.1 + 1.8 = 3.9
• Poisson model gives approximately 55% probability of Over 3.5
• Fair Over 3.5 odds: ~1.83; Fair Under 3.5 odds: ~2.20
• The most likely scorelines are 2-1, 1-1, 2-2, 1-2 and 3-1 — two of them (2-2 and 3-1) already go over 3.5, and the long tail of higher scores pushes Over 3.5 above 50%

Why xG Is Better Than Average Goals Scored

Using a team's raw goals scored average is a common shortcut, but it introduces noise from outlier results. A team that scores 5 goals once in a 10-game sample skews the average significantly. Expected goals (xG) measures the quality of chances, not just the results — making it a more stable and predictive input for the Poisson model. For best results, use rolling xG over the last 5–10 matches rather than season totals, as form and tactical setup evolve.